Pub Date : 2024-03-15DOI: 10.3991/ijoe.v20i05.45609
Sobha Xavier P, Sathish P. K., Raju G
Post-operative brain magnetic resonance imaging (MRI) segmentation is inherently challenging due to the diverse patterns in brain tissue, which makes it difficult to accurately identify resected areas. Therefore, there is a crucial need for a precise segmentation model. Due to the scarcity of post-operative brain MRI scans, it is not feasible to use complex models that require a large amount of training data. This paper introduces an innovative approach for accurately segmenting and quantifying post-operative brain resection cavities in MRI scans. The proposed model, named Attention-Enhanced VGG-U-Net, integrates VGG16 initial weights in the encoder section and incorporates a self-attention module in the decoder, offering improved accuracy for postoperative brain MRI segmentation. The attention mechanism enhances its accuracy by concentrating on a specific area of interest. The VGG16 model is comparatively lightweight, has pre-trained weights, and allows the model to extract incredibly detailed information from the input. The model is trained on publicly available post-operative brain MRI data and achieved a Dice coefficient value of 0.893. The model is then assessed using a clinical dataset of postoperative brain MRIs. The model facilitates the quantification of the resected regions and enables comparisons with each brain region based on pre-operative images. The capabilities of the model assist radiologists in evaluating surgical success and directing follow-up procedures.
{"title":"Post-Operative Brain MRI Resection Cavity Segmentation Model and Follow-Up Treatment Assistance","authors":"Sobha Xavier P, Sathish P. K., Raju G","doi":"10.3991/ijoe.v20i05.45609","DOIUrl":"https://doi.org/10.3991/ijoe.v20i05.45609","url":null,"abstract":"Post-operative brain magnetic resonance imaging (MRI) segmentation is inherently challenging due to the diverse patterns in brain tissue, which makes it difficult to accurately identify resected areas. Therefore, there is a crucial need for a precise segmentation model. Due to the scarcity of post-operative brain MRI scans, it is not feasible to use complex models that require a large amount of training data. This paper introduces an innovative approach for accurately segmenting and quantifying post-operative brain resection cavities in MRI scans. The proposed model, named Attention-Enhanced VGG-U-Net, integrates VGG16 initial weights in the encoder section and incorporates a self-attention module in the decoder, offering improved accuracy for postoperative brain MRI segmentation. The attention mechanism enhances its accuracy by concentrating on a specific area of interest. The VGG16 model is comparatively lightweight, has pre-trained weights, and allows the model to extract incredibly detailed information from the input. The model is trained on publicly available post-operative brain MRI data and achieved a Dice coefficient value of 0.893. The model is then assessed using a clinical dataset of postoperative brain MRIs. The model facilitates the quantification of the resected regions and enables comparisons with each brain region based on pre-operative images. The capabilities of the model assist radiologists in evaluating surgical success and directing follow-up procedures.","PeriodicalId":507997,"journal":{"name":"International Journal of Online and Biomedical Engineering (iJOE)","volume":"8 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140240943","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-15DOI: 10.3991/ijoe.v20i05.46791
Kristell Yukie Jimenez Ayala
Breast cancer is an illness that affects many women and can cause even death; this is a case of not being detected on time, which could be due to a human error during the analysis of radiographic images or not going on time in a health center. For this, using machine learning (ML) to analyze radiographic images is proposed as a support tool for radiologists aiming to reduce false diagnostic rates. While researching information, it was detected that this technology has many benefits in the health area; however, it also has limitations or disadvantages. The importance of this paper is to demonstrate that there are not enough clinical tests nor details about the methodologies that were used; there should be more to assert that ML is defined at the moment of making a diagnosis, which generates no conclusive results regarding effectiveness and therefore creates mistrust in doctors, and some people might rather use deep learning (DL) for its application in the detection of breast cancer because DL has more practical tests and fewer limitations than machine learning.
{"title":"Detection of Breast Cancer through the Analysis of Radiographic Images Using Machine Learning: A Systematic Review","authors":"Kristell Yukie Jimenez Ayala","doi":"10.3991/ijoe.v20i05.46791","DOIUrl":"https://doi.org/10.3991/ijoe.v20i05.46791","url":null,"abstract":"Breast cancer is an illness that affects many women and can cause even death; this is a case of not being detected on time, which could be due to a human error during the analysis of radiographic images or not going on time in a health center. For this, using machine learning (ML) to analyze radiographic images is proposed as a support tool for radiologists aiming to reduce false diagnostic rates. While researching information, it was detected that this technology has many benefits in the health area; however, it also has limitations or disadvantages. The importance of this paper is to demonstrate that there are not enough clinical tests nor details about the methodologies that were used; there should be more to assert that ML is defined at the moment of making a diagnosis, which generates no conclusive results regarding effectiveness and therefore creates mistrust in doctors, and some people might rather use deep learning (DL) for its application in the detection of breast cancer because DL has more practical tests and fewer limitations than machine learning.","PeriodicalId":507997,"journal":{"name":"International Journal of Online and Biomedical Engineering (iJOE)","volume":"23 50","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140240371","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-15DOI: 10.3991/ijoe.v20i05.47171
Ismael M. Abdulkareem, Faris K. AL-Shammri, Noor Aldeen A. Khalid, Natiq A. Omran
Object detection and recognition play a crucial role in computer vision applications, ranging from security systems to autonomous vehicles. Deep learning algorithms have shown remarkable performance in these tasks, but they often require large, annotated datasets for training. However, collecting such datasets can be time-consuming and costly. Data augmentation techniques provide a solution to this problem by artificially expanding the training dataset. In this study, we propose a deep learning approach for object detection and recognition that leverages data augmentation techniques. We use deep convolutional neural networks (CNNs) as the underlying architecture, specifically focusing on popular models such as You Only Look Once version 3 (YOLOv3). By augmenting the training data with various transformations, such as rotation, scaling, and flipping, we can effectively increase the diversity and size of the dataset. Our approach not only improves the robustness and generalization of the models but also reduces the risk of overfitting. By training on augmented data, the models can learn to recognize objects from different viewpoints, scales, and orientations, leading to improved accuracy and performance. We conduct extensive experiments on benchmark datasets and evaluate the performance of our approach using standard metrics such as precision, recall, and mean average precision (mAP). The experimental results demonstrate that our data augmentation-based deep learning approach achieves superior object detection and recognition accuracy compared to traditional training methods without data augmentation. We compare the average accuracy of the YOLOv3-SPP model with two other variants of the YOLOv3 algorithm: one with a feature extraction network consisting of 53 convolutional layers and the other with 13 convolutional layers. The average accuracy of the proposed model (YOLOv3-SPP) is reported as accuracy of 97%, F1-score of 96%, precision of 94%, and average Intersection over Union (IoU) of 78.04%.
从安全系统到自动驾驶汽车，物体检测和识别在计算机视觉应用中发挥着至关重要的作用。深度学习算法在这些任务中表现出了不俗的性能，但它们通常需要大量的注释数据集来进行训练。然而，收集此类数据集既费时又费钱。数据增强技术通过人为扩展训练数据集来解决这一问题。在本研究中，我们提出了一种利用数据增强技术进行物体检测和识别的深度学习方法。我们使用深度卷积神经网络（CNN）作为底层架构，特别关注流行的模型，如 You Only Look Once version 3（YOLOv3）。通过对训练数据进行各种变换（如旋转、缩放和翻转），我们可以有效增加数据集的多样性和规模。我们的方法不仅提高了模型的鲁棒性和泛化能力，还降低了过度拟合的风险。通过在增强数据上进行训练，模型可以学会从不同视角、尺度和方向识别物体，从而提高准确性和性能。我们在基准数据集上进行了广泛的实验，并使用精度、召回率和平均精度（mAP）等标准指标评估了我们方法的性能。实验结果表明，与没有数据增强的传统训练方法相比，我们基于数据增强的深度学习方法实现了更高的物体检测和识别准确率。我们将 YOLOv3-SPP 模型的平均精度与 YOLOv3 算法的其他两个变体进行了比较：一个是由 53 个卷积层组成的特征提取网络，另一个是由 13 个卷积层组成的特征提取网络。据报告，拟议模型（YOLOv3-SPP）的平均准确率为 97%，F1 分数为 96%，精确度为 94%，平均联合交叉率 (IoU) 为 78.04%。
{"title":"Proposed Approach for Object Detection and Recognition by Deep Learning Models Using Data Augmentation","authors":"Ismael M. Abdulkareem, Faris K. AL-Shammri, Noor Aldeen A. Khalid, Natiq A. Omran","doi":"10.3991/ijoe.v20i05.47171","DOIUrl":"https://doi.org/10.3991/ijoe.v20i05.47171","url":null,"abstract":"Object detection and recognition play a crucial role in computer vision applications, ranging from security systems to autonomous vehicles. Deep learning algorithms have shown remarkable performance in these tasks, but they often require large, annotated datasets for training. However, collecting such datasets can be time-consuming and costly. Data augmentation techniques provide a solution to this problem by artificially expanding the training dataset. In this study, we propose a deep learning approach for object detection and recognition that leverages data augmentation techniques. We use deep convolutional neural networks (CNNs) as the underlying architecture, specifically focusing on popular models such as You Only Look Once version 3 (YOLOv3). By augmenting the training data with various transformations, such as rotation, scaling, and flipping, we can effectively increase the diversity and size of the dataset. Our approach not only improves the robustness and generalization of the models but also reduces the risk of overfitting. By training on augmented data, the models can learn to recognize objects from different viewpoints, scales, and orientations, leading to improved accuracy and performance. We conduct extensive experiments on benchmark datasets and evaluate the performance of our approach using standard metrics such as precision, recall, and mean average precision (mAP). The experimental results demonstrate that our data augmentation-based deep learning approach achieves superior object detection and recognition accuracy compared to traditional training methods without data augmentation. We compare the average accuracy of the YOLOv3-SPP model with two other variants of the YOLOv3 algorithm: one with a feature extraction network consisting of 53 convolutional layers and the other with 13 convolutional layers. The average accuracy of the proposed model (YOLOv3-SPP) is reported as accuracy of 97%, F1-score of 96%, precision of 94%, and average Intersection over Union (IoU) of 78.04%.","PeriodicalId":507997,"journal":{"name":"International Journal of Online and Biomedical Engineering (iJOE)","volume":"24 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140240357","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-15DOI: 10.3991/ijoe.v20i05.48229
Imad Tareq, B. Elbagoury, S. El-Regaily, El-Sayed M. El-Horbaty
Recently, there has been a growing concern regarding the detrimental effects of cyberattacks on both infrastructure and users. Conventional safety measures, such as encryption, firewalls, and intrusion detection, are inadequate to safeguard cyber systems against emerging and evolving threats. To address this issue, researchers have turned to reinforcement learning (RL) as a potential solution for complex decision-making problems in cybersecurity. However, the application of RL faces various obstacles, including a lack of suitable training data, dynamic attack scenarios, and challenges in modeling real-world complexities. This paper suggests applying deep reinforcement learning (DRL), a deep framework, to simulate malicious cyberattacks and enhance cybersecurity. Our framework utilizes an agent-based model that is capable of continuous learning and adaptation within a dynamic network security environment. The agent determines the most optimal course of action based on the network’s state and the corresponding rewards received for its decisions. We present the outcomes of our experimentation with the application of DRL on a specific model, double deep Q-network (DDQN), utilizing policy gradient (PG) on three distinct datasets: NSL-KDD, CIC-IDS-2018, and AWID. Our research demonstrates that DRL can effectively improve cyberattack detection outcomes through our model and specific parameter adjustments.
{"title":"Deep Reinforcement Learning Approach for Cyberattack Detection","authors":"Imad Tareq, B. Elbagoury, S. El-Regaily, El-Sayed M. El-Horbaty","doi":"10.3991/ijoe.v20i05.48229","DOIUrl":"https://doi.org/10.3991/ijoe.v20i05.48229","url":null,"abstract":"Recently, there has been a growing concern regarding the detrimental effects of cyberattacks on both infrastructure and users. Conventional safety measures, such as encryption, firewalls, and intrusion detection, are inadequate to safeguard cyber systems against emerging and evolving threats. To address this issue, researchers have turned to reinforcement learning (RL) as a potential solution for complex decision-making problems in cybersecurity. However, the application of RL faces various obstacles, including a lack of suitable training data, dynamic attack scenarios, and challenges in modeling real-world complexities. This paper suggests applying deep reinforcement learning (DRL), a deep framework, to simulate malicious cyberattacks and enhance cybersecurity. Our framework utilizes an agent-based model that is capable of continuous learning and adaptation within a dynamic network security environment. The agent determines the most optimal course of action based on the network’s state and the corresponding rewards received for its decisions. We present the outcomes of our experimentation with the application of DRL on a specific model, double deep Q-network (DDQN), utilizing policy gradient (PG) on three distinct datasets: NSL-KDD, CIC-IDS-2018, and AWID. Our research demonstrates that DRL can effectively improve cyberattack detection outcomes through our model and specific parameter adjustments.","PeriodicalId":507997,"journal":{"name":"International Journal of Online and Biomedical Engineering (iJOE)","volume":"125 13","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140237679","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-15DOI: 10.3991/ijoe.v20i05.45547
N. Nuryani, T. P. Utomo, N. Prabowo, Aripriharta, Muhammad Yazid, Mohtar Yunianto
Timely identification of hypertension (HT) is crucial for effectively managing and reducing the potential health consequences, including cardiovascular events such as heart attacks and strokes, as well as the development of kidney disease. Traditional cuff-based devices often discourage regular monitoring because they cause discomfort. Furthermore, the lack of symptoms in HT complicates the early detection of this condition. To address these challenges, our study employs a non-cuff methodology that utilizes unprocessed electrocardiogram (ECG) and photoplethysmogram (PPG) signals. We utilize a customized approach to enhance the features of a one-dimensional convolutional neural network (CNN) specifically tailored to optimize timeseries data. In contrast to previous research, our methodology avoids the need for complex signal extraction or transformation techniques. The main goal is to identify the optimal input signals and fine-tune the critical hyperparameters of CNNs. The clinical data underwent analysis, which revealed that the use of an integrated ECG and PPG approach resulted in the highest level of accuracy for detection. Notably, the F1 score achieved an impressive value of 98.88%. When evaluated separately, ECG outperformed PPG. Our study contributes to the advancement of the field by introducing a new approach that combines comfort and high accuracy in the early detection of HT. This method is practical and ensures a patient-friendly experience.
{"title":"Advancing Non-Cuff Hypertension Detection: Leveraging 1D Convolutional Neural Network and Time Domain Physiological Signals","authors":"N. Nuryani, T. P. Utomo, N. Prabowo, Aripriharta, Muhammad Yazid, Mohtar Yunianto","doi":"10.3991/ijoe.v20i05.45547","DOIUrl":"https://doi.org/10.3991/ijoe.v20i05.45547","url":null,"abstract":"Timely identification of hypertension (HT) is crucial for effectively managing and reducing the potential health consequences, including cardiovascular events such as heart attacks and strokes, as well as the development of kidney disease. Traditional cuff-based devices often discourage regular monitoring because they cause discomfort. Furthermore, the lack of symptoms in HT complicates the early detection of this condition. To address these challenges, our study employs a non-cuff methodology that utilizes unprocessed electrocardiogram (ECG) and photoplethysmogram (PPG) signals. We utilize a customized approach to enhance the features of a one-dimensional convolutional neural network (CNN) specifically tailored to optimize timeseries data. In contrast to previous research, our methodology avoids the need for complex signal extraction or transformation techniques. The main goal is to identify the optimal input signals and fine-tune the critical hyperparameters of CNNs. The clinical data underwent analysis, which revealed that the use of an integrated ECG and PPG approach resulted in the highest level of accuracy for detection. Notably, the F1 score achieved an impressive value of 98.88%. When evaluated separately, ECG outperformed PPG. Our study contributes to the advancement of the field by introducing a new approach that combines comfort and high accuracy in the early detection of HT. This method is practical and ensures a patient-friendly experience.","PeriodicalId":507997,"journal":{"name":"International Journal of Online and Biomedical Engineering (iJOE)","volume":"12 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140239394","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-15DOI: 10.3991/ijoe.v20i05.45277
G. Maquen-Niño, Jhojan Genaro Nuñez-Fernandez, Fany Yesica Taquila-Calderon, Ivan Adrianzén-Olano, Percy De-La-Cruz-VdV, Gilberto Carrión-Barco
In the current global context, there has been a significant increase in respiratory system diseases, particularly pneumonia. This disease has a higher incidence of mortality in children under five years old and adults over 60 years old because it leads to complications if not treated in time. This research leverages convolutional neural networks (CNNs) to classify images, specifically to detect the presence of pneumonia. The data processing methodology utilized in this study is CRISP-DM. The dataset consists of 5,856 images of anteroposterior chest X-rays downloaded from the open repository “Kaggle,” divided into 5,216 images for training, 16 for validation, and 624 for testing. Preprocessing involved image augmentation through modifications to the original images, scaling, and batch division in tensor format. A comparative analysis was conducted among the transfer models: DenseNet, VGG19, and ResNet50 version 2. Each transfer model was the header of a CNN with four subsequent layers. The models underwent training, validation, and testing phases. The test’s results showed that DenseNet achieved an accuracy of 0.87, VGG19 achieved 0.86, and ResNet50 achieved 0.91. These results affirm the effectiveness of ResNet50 in image classification, considering that the model’s output is binary, where 0 represents that the patient does not have pneumonia and 1 indicates that the patient has pneumonia.
{"title":"Classification Model Using Transfer Learning for the Detection of Pneumonia in Chest X-Ray Images","authors":"G. Maquen-Niño, Jhojan Genaro Nuñez-Fernandez, Fany Yesica Taquila-Calderon, Ivan Adrianzén-Olano, Percy De-La-Cruz-VdV, Gilberto Carrión-Barco","doi":"10.3991/ijoe.v20i05.45277","DOIUrl":"https://doi.org/10.3991/ijoe.v20i05.45277","url":null,"abstract":"In the current global context, there has been a significant increase in respiratory system diseases, particularly pneumonia. This disease has a higher incidence of mortality in children under five years old and adults over 60 years old because it leads to complications if not treated in time. This research leverages convolutional neural networks (CNNs) to classify images, specifically to detect the presence of pneumonia. The data processing methodology utilized in this study is CRISP-DM. The dataset consists of 5,856 images of anteroposterior chest X-rays downloaded from the open repository “Kaggle,” divided into 5,216 images for training, 16 for validation, and 624 for testing. Preprocessing involved image augmentation through modifications to the original images, scaling, and batch division in tensor format. A comparative analysis was conducted among the transfer models: DenseNet, VGG19, and ResNet50 version 2. Each transfer model was the header of a CNN with four subsequent layers. The models underwent training, validation, and testing phases. The test’s results showed that DenseNet achieved an accuracy of 0.87, VGG19 achieved 0.86, and ResNet50 achieved 0.91. These results affirm the effectiveness of ResNet50 in image classification, considering that the model’s output is binary, where 0 represents that the patient does not have pneumonia and 1 indicates that the patient has pneumonia.","PeriodicalId":507997,"journal":{"name":"International Journal of Online and Biomedical Engineering (iJOE)","volume":"22 23","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140240544","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-15DOI: 10.3991/ijoe.v20i05.48225
Minning Wu, Eric B. Blancaflor, Fei Ren, Yong Wang, Ting Dong
In the pivotal water resource region of the Yellow River Basin in China, precise prediction of water resources is essential for their effective and rational management. This study introduces a novel approach to water resource prediction by employing the Harris Hawks Optimization-Long Short-Term Memory (HHO-LSTM) model. This method overcomes the constraints faced by traditional techniques in processing time series data and various variable factors. It encompasses a comprehensive description of the multi-source hydrological data collection process within the Yellow River Basin, followed by meticulous data preprocessing. The data set for this study includes estimates of four critical water quality parameters, and the efficacy of the model is gauged through the mean squared error (MSE) and root mean squared error (RMSE) metrics. This facilitates the projection of future water quality trends in specific areas by leveraging historical water quality data. The HHO-LSTM model has demonstrated outstanding accuracy and robustness in predicting water quality across diverse temporal scales and water resource variables, marking a significant advancement in water resource management within the Yellow River Basin. This approach not only enhances current management strategies but also contributes valuable insights for ongoing water resource research and decision-making processes.
{"title":"Enhanced Water Quality Prediction in the Yellow River Basin: The Application of the HHO-LSTM Model","authors":"Minning Wu, Eric B. Blancaflor, Fei Ren, Yong Wang, Ting Dong","doi":"10.3991/ijoe.v20i05.48225","DOIUrl":"https://doi.org/10.3991/ijoe.v20i05.48225","url":null,"abstract":"In the pivotal water resource region of the Yellow River Basin in China, precise prediction of water resources is essential for their effective and rational management. This study introduces a novel approach to water resource prediction by employing the Harris Hawks Optimization-Long Short-Term Memory (HHO-LSTM) model. This method overcomes the constraints faced by traditional techniques in processing time series data and various variable factors. It encompasses a comprehensive description of the multi-source hydrological data collection process within the Yellow River Basin, followed by meticulous data preprocessing. The data set for this study includes estimates of four critical water quality parameters, and the efficacy of the model is gauged through the mean squared error (MSE) and root mean squared error (RMSE) metrics. This facilitates the projection of future water quality trends in specific areas by leveraging historical water quality data. The HHO-LSTM model has demonstrated outstanding accuracy and robustness in predicting water quality across diverse temporal scales and water resource variables, marking a significant advancement in water resource management within the Yellow River Basin. This approach not only enhances current management strategies but also contributes valuable insights for ongoing water resource research and decision-making processes.","PeriodicalId":507997,"journal":{"name":"International Journal of Online and Biomedical Engineering (iJOE)","volume":"53 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140238380","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-15DOI: 10.3991/ijoe.v20i05.43257
C. Baidada, Mustapha Aatila, M. Lachgar, Hamid Hrimech, Younes Ommane, Abderrahim Houlali
Effective time and resource management is crucial not only in the operating room but also in healthcare supply chains. Healthcare supply chains involve the movement of medical supplies, equipment, and medications from manufacturers to healthcare providers. Effective management is crucial to ensuring that patients receive the care they need promptly. In the operating room, it is essential to have an information process in place to effectively manage time and resources during the current surgical procedure. This paper focuses on developing a predictive model for the operating time of flexible ureteroscopy for kidney stones. The model can forecast surgical and preoperative time based on patient characteristics and surgeon experience. The model can assist in planning ureteroscopy procedures and preventing surgical complications, which is crucial not only for the operating room but also for healthcare supply chains. The paper presents a study that compares different feature selection methods and regression techniques. The study found that sequential backward selection combined with the extra tree regressor was the most effective approach.
{"title":"Flexible Ureteroscopy Lithotripsy Operative Time Prediction Model for the Treatment of Kidney Stones","authors":"C. Baidada, Mustapha Aatila, M. Lachgar, Hamid Hrimech, Younes Ommane, Abderrahim Houlali","doi":"10.3991/ijoe.v20i05.43257","DOIUrl":"https://doi.org/10.3991/ijoe.v20i05.43257","url":null,"abstract":"Effective time and resource management is crucial not only in the operating room but also in healthcare supply chains. Healthcare supply chains involve the movement of medical supplies, equipment, and medications from manufacturers to healthcare providers. Effective management is crucial to ensuring that patients receive the care they need promptly. In the operating room, it is essential to have an information process in place to effectively manage time and resources during the current surgical procedure. This paper focuses on developing a predictive model for the operating time of flexible ureteroscopy for kidney stones. The model can forecast surgical and preoperative time based on patient characteristics and surgeon experience. The model can assist in planning ureteroscopy procedures and preventing surgical complications, which is crucial not only for the operating room but also for healthcare supply chains. The paper presents a study that compares different feature selection methods and regression techniques. The study found that sequential backward selection combined with the extra tree regressor was the most effective approach.","PeriodicalId":507997,"journal":{"name":"International Journal of Online and Biomedical Engineering (iJOE)","volume":"25 30","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140240255","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Cardiovascular diseases are the leading cause of death worldwide. Therefore, this study aims to develop a mobile application utilizing the Internet of Things (IoT) to monitor patients’ heart rate. The study employed a quantitative approach and a pre-experimental design. The experiment was conducted according to the research plan and involved 20 patients. The Scrum methodology was used for the development of the mobile application. The results reveal a significant improvement in patient and family satisfaction after using the IoT-enabled mobile application. In addition, the average measurement time has decreased to 6.025 minutes, which represents a significant difference compared to the traditional method. The number of measurements has increased from seven to 14 per week, averaging two regular daily measurements. The measurement device has alleviated the concerns of family members who are taking care of loved ones with cardiovascular disease. This tool gives users greater peace of mind, enabling them to take accurate and reliable measurements 24/7.
{"title":"Remote Heart Rate Monitoring Device Using the Internet of Things","authors":"Orlando Iparraguirre-Villanueva, Enrique Surcco-Jacinto, Melanie Balvin-Chávez","doi":"10.3991/ijoe.v20i05.46857","DOIUrl":"https://doi.org/10.3991/ijoe.v20i05.46857","url":null,"abstract":"Cardiovascular diseases are the leading cause of death worldwide. Therefore, this study aims to develop a mobile application utilizing the Internet of Things (IoT) to monitor patients’ heart rate. The study employed a quantitative approach and a pre-experimental design. The experiment was conducted according to the research plan and involved 20 patients. The Scrum methodology was used for the development of the mobile application. The results reveal a significant improvement in patient and family satisfaction after using the IoT-enabled mobile application. In addition, the average measurement time has decreased to 6.025 minutes, which represents a significant difference compared to the traditional method. The number of measurements has increased from seven to 14 per week, averaging two regular daily measurements. The measurement device has alleviated the concerns of family members who are taking care of loved ones with cardiovascular disease. This tool gives users greater peace of mind, enabling them to take accurate and reliable measurements 24/7.","PeriodicalId":507997,"journal":{"name":"International Journal of Online and Biomedical Engineering (iJOE)","volume":"10 13","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140240848","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-15DOI: 10.3991/ijoe.v20i05.47793
Mohamad Ariffin Abu Bakar, Ahmad Termimi Ab Ghani, Mohd Lazim Abdullah
This study proposed a novel framework for redesigning problem-solving activities in an intelligent tutoring system (ITS) called the intelligent neural-mechanistic mathematics problem- solving tutoring system (IN-MP-STS). This concept paper presents a new approach to ITS by incorporating elements of neuroscience mechanisms as a learning strategy that focuses on optimizing the brain’s ability through neural mechanisms. It also introduces fuzzy neural networks (FNNs) as a tool for modulating assessment and analyzing outcomes. This framework offers an alternative perspective on delivery methods and learning approaches in the ITS module. By effectively integrating neuroscience mechanistic elements such as motivation, activation, regulation, execution, memorization, and interactivities, deep learning can be achieved, leading to improved student competence. This framework also proposes an adaptive assessment component based on FNNs, which will enhance the measurement and feedback modules in the system. It is necessary to modify the way that ITS and soft computing methods, such as the study of neural networks (NNs), are combined to make learning measurement and assessment more transparent. This innovation has not been fully disclosed, so researchers are encouraged to further test the concepts presented to assess their alignment with the existing system and ethical considerations. This framework enhances the conceptual research findings of FNNs and incorporates neuroscience-based strategies into architecture and autonomous problem-solving skills within an ITS model. It also offers references for the development of problem-solving learning. IN-MP-STS has the potential to significantly enhance students’ competencies and abilities, thereby fostering the development of more comprehensive, holistic, and sustainable ITS. This approach also has the potential to enrich the existing literature on the sustainability of neural networks.
本研究提出了一个新颖的框架，用于重新设计智能辅导系统（ITS）中的问题解决活动，该系统被称为智能神经机制数学问题解决辅导系统（IN-MP-STS）。这篇概念论文提出了一种新的智能辅导系统方法，它将神经科学机制的元素作为一种学习策略，侧重于通过神经机制优化大脑的能力。它还引入了模糊神经网络（FNN）作为调节评估和分析结果的工具。这一框架为 ITS 模块中的授课方式和学习方法提供了另一种视角。通过有效整合动机、激活、调节、执行、记忆和互动等神经科学机制要素，可以实现深度学习，从而提高学生的能力。该框架还提出了基于 FNN 的自适应评估组件，这将增强系统中的测量和反馈模块。有必要修改智能学习系统和软计算方法（如神经网络研究）的结合方式，使学习测量和评估更加透明。这一创新尚未完全公开，因此鼓励研究人员进一步测试所提出的概念，以评估其与现有系统和伦理考虑的一致性。该框架增强了 FNN 的概念研究成果，并将基于神经科学的策略纳入了 ITS 模型中的架构和自主解决问题的技能。它还为问题解决学习的发展提供了参考。IN-MP-STS 有可能显著提高学生的能力和才干，从而促进更全面、整体和可持续的 ITS 的发展。这种方法还有可能丰富现有关于神经网络可持续性的文献。
{"title":"An Intelligent Mathematics Problem-Solving Tutoring System Framework","authors":"Mohamad Ariffin Abu Bakar, Ahmad Termimi Ab Ghani, Mohd Lazim Abdullah","doi":"10.3991/ijoe.v20i05.47793","DOIUrl":"https://doi.org/10.3991/ijoe.v20i05.47793","url":null,"abstract":"This study proposed a novel framework for redesigning problem-solving activities in an intelligent tutoring system (ITS) called the intelligent neural-mechanistic mathematics problem- solving tutoring system (IN-MP-STS). This concept paper presents a new approach to ITS by incorporating elements of neuroscience mechanisms as a learning strategy that focuses on optimizing the brain’s ability through neural mechanisms. It also introduces fuzzy neural networks (FNNs) as a tool for modulating assessment and analyzing outcomes. This framework offers an alternative perspective on delivery methods and learning approaches in the ITS module. By effectively integrating neuroscience mechanistic elements such as motivation, activation, regulation, execution, memorization, and interactivities, deep learning can be achieved, leading to improved student competence. This framework also proposes an adaptive assessment component based on FNNs, which will enhance the measurement and feedback modules in the system. It is necessary to modify the way that ITS and soft computing methods, such as the study of neural networks (NNs), are combined to make learning measurement and assessment more transparent. This innovation has not been fully disclosed, so researchers are encouraged to further test the concepts presented to assess their alignment with the existing system and ethical considerations. This framework enhances the conceptual research findings of FNNs and incorporates neuroscience-based strategies into architecture and autonomous problem-solving skills within an ITS model. It also offers references for the development of problem-solving learning. IN-MP-STS has the potential to significantly enhance students’ competencies and abilities, thereby fostering the development of more comprehensive, holistic, and sustainable ITS. This approach also has the potential to enrich the existing literature on the sustainability of neural networks.","PeriodicalId":507997,"journal":{"name":"International Journal of Online and Biomedical Engineering (iJOE)","volume":"13 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140241041","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：